Methods and systems of routing utterances based on confidence estimates
    1.
    发明授权
    Methods and systems of routing utterances based on confidence estimates 有权
    基于置信估计路由话语的方法和系统

    公开(公告)号:US07003456B2

    公开(公告)日:2006-02-21

    申请号:US09878173

    申请日:2001-06-12

    IPC分类号: G10L15/26

    CPC分类号: G10L15/32 G10L15/10

    摘要: A computer-based method of routing a message to a system includes receiving a message, and processing the message using large-vocabulary continuous speech recognition to generate a string of text corresponding to the message. The method includes generating a confidence estimate of the string of text corresponding to the message and comparing the confidence estimate to a predetermined threshold. If the confidence estimate satisfies the predetermined threshold, the string of text is forwarded to the system. If the confidence estimate does not satisfy the predetermined threshold, the information relating to the message is forwarded to a transcriptionist. The message may include one or more utterances. Each utterance in the message may be separately or jointly processed. In this way, a confidence estimate may be generated and evaluated for each utterance or for the whole message. Information relating to each utterance may be separately or jointly forwarded based on the results of the generation and evaluation.

    摘要翻译: 将消息路由到系统的基于计算机的方法包括接收消息,以及使用大词汇连续语音识别处理消息以生成与消息对应的文本串。 该方法包括生成对应于消息的文本串的置信估计,并将置信度估计与预定阈值进行比较。 如果置信度估计满足预定阈值,那么文本串将被转发给系统。 如果置信度估计不满足预定阈值,与消息相关的信息被转发给记录者。 消息可以包括一个或多个话语。 消息中的每个话语可以单独或联合处理。 以这种方式,可以为每个话语或整个消息产生和评估置信估计。 与每个话语有关的信息可以根据生成和评估的结果单独或共同转发。

    Lexical tree pre-filtering in speech recognition
    2.
    发明授权
    Lexical tree pre-filtering in speech recognition 失效
    词汇树预处理语音识别

    公开(公告)号:US5822730A

    公开(公告)日:1998-10-13

    申请号:US701393

    申请日:1996-08-22

    IPC分类号: G10L15/08 G10L15/18 G10L5/06

    摘要: A speech recognition technique uses lexical tree pre-filtering to obtain lists of words for use in performing speech recognition. The lexical tree pre-filtering includes representing a vocabulary of words using a lexical tree and identifying a first subset of the vocabulary that may correspond to speech spoken beginning at a first time by propagating through the lexical tree information about the speech spoken beginning at the first time. A second subset of the vocabulary that may correspond to speech spoken beginning at a second time is identified by propagating through the lexical tree information about the speech spoken beginning at the second time. Words included in the speech are recognized by comparing speech spoken beginning at the first time with words from the first subset of the vocabulary and speech spoken beginning at the second time with words from the second subset of the vocabulary. The state of the lexical tree is not reset between identifying the first and second subsets.

    摘要翻译: 语音识别技术使用词法树预滤波来获得用于执行语音识别的单词列表。 词汇树预过滤包括使用词汇树表示单词的词汇表,并通过从第一时间开始通过词汇树传播关于所说出的语音的信息来识别可能对应于在第一时间开始讲的语音的词汇表的第一子集 时间。 可以对应于在第二时间开始的语音对应的词汇表的第二个子集通过从第二次开始的词汇传播通过词汇树信息来识别。 包括在语音中的词通过比较从第一次开始的语音与来自第二时间开始的词汇的第一个子集和来自词汇的第二个子集的单词的语言进行比较来识别。 在识别第一和第二个子集之间,词汇树的状态不会被重置。

    Method of producing alternate utterance hypotheses using auxiliary information on close competitors
    3.
    发明授权
    Method of producing alternate utterance hypotheses using auxiliary information on close competitors 有权
    使用辅助信息在密切的竞争对手上产生替代发音假设的方法

    公开(公告)号:US07676367B2

    公开(公告)日:2010-03-09

    申请号:US10783518

    申请日:2004-02-20

    IPC分类号: G10L15/04 G10L15/00

    摘要: A method of constructing a list of alternate transcripts from a recognized transcript includes generating a list of close call records, matching partial sub-histories from the recognized transcript with one of the history pairs stored in each of the records, and substituting the other of the history pairs for the partial sub-history of the recognized transcript. A close call record is generated each time a pair of partial hypotheses attempt to seed a common word. Each close call record includes history information and scoring information associated with a particular pair of partial hypotheses seeding a common word. Alternate transcripts are constructed by substituting close call histories for partial histories of the recognized transcripts, and also by substituting close call histories for partial histories of other alternate transcript.

    摘要翻译: 从识别的记录中构建候选抄本的列表的方法包括生成紧密呼叫记录的列表,将来自所识别抄本的部分子历史与存储在每个记录中的历史对之一进行匹配, 历史对对于识别的成绩单的部分子历史记录。 每当一对部分假设尝试种植一个共同词时,就会产生一个接近通话记录。 每个近距离通话记录包括历史信息和与特定的一对部分假设相关联的评分信息,播种公共字。 替代的成绩单是通过将认可的记录的部分历史代替关闭呼叫历史,并通过替代其他替代记录的部分历史的近距离呼叫历史来代替。

    Transaction detection in link based computing system
    5.
    发明授权
    Transaction detection in link based computing system 有权
    基于链接的计算系统中的事务检测

    公开(公告)号:US07813288B2

    公开(公告)日:2010-10-12

    申请号:US11284459

    申请日:2005-11-21

    IPC分类号: G01R31/08

    CPC分类号: G06F11/2236

    摘要: A transaction detection device is described having inputs to couple to communication lines. Each communication line to transport notification of a packet observed by a link probe within a computing system containing point-to-point links between nodes. Each of said nodes having at least one processing core. The transaction detection device also comprises logic circuitry to determine from said notifications whether a looked for transaction has occurred within said computing system.

    摘要翻译: 描述具有用于耦合到通信线路的输入的交易检测装置。 每个通信线路在包含节点之间的点对点链路的计算系统内传送由链路探测器观察到的分组的通知。 每个所述节点具有至少一个处理核。 事务检测设备还包括逻辑电路,用于从所述通知确定在所述计算系统内是否发生了寻找的事务。

    Pressure regulator assembly
    6.
    发明申请
    Pressure regulator assembly 审中-公开
    压力调节器总成

    公开(公告)号:US20050061372A1

    公开(公告)日:2005-03-24

    申请号:US10932763

    申请日:2004-09-02

    IPC分类号: F16K15/04 F16K17/04 G05D16/10

    摘要: A pressure regulator assembly for a fluid system includes a housing having at least one cavity therein and a valve seat disposed in the at least one cavity and having an aperture extending therethrough. The pressure regulator assembly also includes a movable valve member disposed in the at least one cavity of the housing. The valve member has a closed position to engage the valve seat to prevent fluid from flowing into the at least one cavity and an open position to disengage the valve seat to allow fluid to flow into the at least one cavity. The pressure regulator assembly further includes a biasing mechanism disposed in the at least one cavity to bias the valve member toward the valve seat to close the aperture. The valve seat and the valve member and the biasing mechanism are aligned linearly along an axis of the valve housing.

    摘要翻译: 用于流体系统的压力调节器组件包括其中具有至少一个空腔的壳体和设置在所述至少一个空腔中并具有延伸穿过其中的孔的阀座。 压力调节器组件还包括设置在壳体的至少一个空腔中的可移动阀构件。 阀构件具有闭合位置以接合阀座以防止流体流入至少一个空腔中,并且打开位置以使阀座脱离以允许流体流入至少一个空腔。 压力调节器组件还包括设置在至少一个空腔中的偏置机构,以将阀构件偏压到阀座以关闭孔。 阀座和阀构件以及偏压机构沿着阀壳体的轴线线性对准。

    Embedded system for construction of small footprint speech recognition with user-definable constraints
    7.
    发明授权
    Embedded system for construction of small footprint speech recognition with user-definable constraints 有权
    嵌入式系统用于构建具有用户可定义约束的小尺寸语音识别

    公开(公告)号:US09117449B2

    公开(公告)日:2015-08-25

    申请号:US13456959

    申请日:2012-04-26

    摘要: Techniques disclosed herein include systems and methods that enable a voice trigger that wakes-up an electronic device or causes the device to make additional voice commands active, without manual initiation of voice command functionality. In addition, such a voice trigger is dynamically programmable or customizable. A speaker can program or designate a particular phrase as the voice trigger. In general, techniques herein execute a voice-activated wake-up system that operates on a digital signal processor (DSP) or other low-power, secondary processing unit of an electronic device instead of running on a central processing unit (CPU). A speech recognition manager runs two speech recognition systems on an electronic device. The CPU dynamically creates a compact speech system for the DSP. Such a compact system can be continuously run during a standby mode, without quickly exhausting a battery supply.

    摘要翻译: 本文公开的技术包括启用语音触发的系统和方法,其唤醒电子设备或使得设备使附加语音命令有效,而无需手动启动语音命令功能。 此外,这样的语音触发器是可动态编程的或可定制的。 扬声器可以将特定短语编程或指定为语音触发。 通常,这里的技术执行语音激活的唤醒系统,其在电子设备的数字信号处理器(DSP)或其他低功率二次处理单元上操作,而不是在中央处理单元(CPU)上运行。 语音识别管理器在电子设备上运行两个语音识别系统。 CPU为DSP动态创建一个紧凑的语音系统。 这样紧凑的系统可以在待机模式下连续运行,而不会快速耗尽电池电源。

    STATIONARY PHASE MATERIALS FOR MICRO GAS ANALYZER
    10.
    发明申请
    STATIONARY PHASE MATERIALS FOR MICRO GAS ANALYZER 有权
    微气体分析仪的静态相材料

    公开(公告)号:US20060228261A1

    公开(公告)日:2006-10-12

    申请号:US11276399

    申请日:2006-02-27

    IPC分类号: B32B5/02 G01N7/00

    摘要: Selecting a stationary phase for a fluid analyzer using certain criteria to determine an appropriate material for use in, for instance, a micro fluid analyzer. High absorption of an analyte or sample, low water sorbency and high porosity or permeability of the material may be sought. A selected material may incorporate a toughening agent using a neutral leaving group. A selected material may have a capping agent to promote hydrophobicity. A selected material may be a hydrophobic polymer. The selection of a stationary phase may involve molecular modeling.

    摘要翻译: 使用某些标准选择用于流体分析仪的固定相,以确定用于例如微流体分析仪的适当材料。 可以寻求分析物或样品的高吸收性,低吸水性和材料的高孔隙率或渗透性。 选择的材料可以使用中性离去基团掺入增韧剂。 选择的材料可以具有封端剂以促进疏水性。 所选择的材料可以是疏水性聚合物。 固定相的选择可能涉及分子建模。